Training in progress epoch 65

README.md

@@ -14,14 +14,14 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0160
-- Train Dice Coef: 0.8038
-- Train Iou: 0.6812
+- Train Loss: 0.0159
+- Train Dice Coef: 0.8084
+- Train Iou: 0.6865
 - Validation Loss: 0.0225
-- Validation Dice Coef: 0.8567
-- Validation Iou: 0.7514
+- Validation Dice Coef: 0.8561
+- Validation Iou: 0.7508
 - Train Lr: 1e-10
-- Epoch: 64
+- Epoch: 65
 
 ## Model description
 
@@ -112,6 +112,7 @@ The following hyperparameters were used during training:
 | 0.0161     | 0.8057          | 0.6830    | 0.0229          | 0.8561               | 0.7507         | 1e-10    | 62    |
 | 0.0160     | 0.8046          | 0.6817    | 0.0230          | 0.8566               | 0.7514         | 1e-10    | 63    |
 | 0.0160     | 0.8038          | 0.6812    | 0.0225          | 0.8567               | 0.7514         | 1e-10    | 64    |
+| 0.0159     | 0.8084          | 0.6865    | 0.0225          | 0.8561               | 0.7508         | 1e-10    | 65    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b939b1099d283e321a53d94cb761bdadbcbc0443c0c91d11ecda909d312ab5e
+oid sha256:45037b687c4cf6d7c8bbbfd3bc0fc42e6bbc36402425cc8626fc870cb3a95b07
 size 15133664